CVPR - arXivDaily 期刊&会议

2104.01108 2021-05-11 cs.CV

Group Collaborative Learning for Co-Salient Object Detection

Qi Fan, Deng-Ping Fan, Huazhu Fu, Chi Keung Tang, Ling Shao, Yu-Wing Tai

Comments Accepted to CVPR 2021. Project page: https://github.com/fanq15/GCoNet Note: corrected Fig 9 in this version

2103.02603 2021-05-11 cs.CV cs.AI cs.LG

Towards Open World Object Detection

K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian

Comments To appear in CVPR 2021 as an ORAL paper. Code is available in https://github.com/JosephKJ/OWOD

2105.03236 2021-05-10 cs.CV

Towards Accurate Text-based Image Captioning with Content Diversity Exploration

Guanghui Xu, Shuaicheng Niu, Mingkui Tan, Yucheng Luo, Qing Du, Qi Wu

Comments Accepted by CVPR 2021

2105.03211 2021-05-10 cs.CV

NeRD: Neural 3D Reflection Symmetry Detector

Yichao Zhou, Shichen Liu, Yi Ma

Comments CVPR 2021. overlaps with arXiv:2006.10042

2105.03136 2021-05-10 cs.CV

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Parth Kothari, Brian Sifringer, Alexandre Alahi

Comments To appear in Computer Vision and Pattern Recognition (CVPR) 2021

2105.03120 2021-05-10 cs.CV cs.LG

Neural 3D Scene Compression via Model Compression

Berivan Isik

Comments Stanford CS 231A Final Project, 2021. WiCV at CVPR 2021

2105.02976 2021-05-10 cs.CV cs.GR

LASR: Learning Articulated Shape Reconstruction from a Monocular Video

Gengshan Yang, Deqing Sun, Varun Jampani, Daniel Vlasic, Forrester Cole, Huiwen Chang, Deva Ramanan, William T. Freeman, Ce Liu

Comments CVPR 2021. Project page: https://lasr-google.github.io/

2105.02965 2021-05-10 cs.LG cs.AI

Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders

Felix Möller, Diego Botache, Denis Huseljic, Florian Heidecker, Maarten Bieshaar, Bernhard Sick

Comments 10 pages, 7 figures, accepted for publication at CVPR 2021 Workshop Safe Artificial Intelligence for Automated Driving (SAIAD)

2012.00417 2021-05-10 cs.CV

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Yuyang Zhao, Zhun Zhong, Fengxiang Yang, Zhiming Luo, Yaojin Lin, Shaozi Li, Nicu Sebe

Comments CVPR 2021

2105.02875 2021-05-07 cs.CV cs.GR cs.LG

Deep Polarization Imaging for 3D shape and SVBRDF Acquisition

Valentin Deschaintre, Yiming Lin, Abhijeet Ghosh

Comments CVPR 2021 Oral paper

2105.02545 2021-05-07 cs.CV

Unsupervised Visual Representation Learning by Tracking Patches in Video

Guangting Wang, Yizhou Zhou, Chong Luo, Wenxuan Xie, Wenjun Zeng, Zhiwei Xiong

Comments To appear in CVPR'21. Code available at github.com/microsoft/CtP

2012.09340 2021-05-07 cs.CV

Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses

Yiming Qian, Hao Zhang, Yasutaka Furukawa

Comments CVPR 2021

2012.01203 2021-05-07 cs.CV cs.GR

Learning Delaunay Surface Elements for Mesh Reconstruction

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov

Journal ref CVPR 2021

2105.02465 2021-05-07 cs.CV

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

Kehong Gong, Jianfeng Zhang, Jiashi Feng

Comments CVPR 2021 Oral Paper, code available: https://github.com/jfzhang95/PoseAug

2105.02440 2021-05-07 cs.CV

Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark

Longyin Wen, Dawei Du, Pengfei Zhu, Qinghua Hu, Qilong Wang, Liefeng Bo, Siwei Lyu

Comments Accpted to CVPR 2021. Dataset and codes can be found in https://github.com/VisDrone/DroneCrowd. arXiv admin note: text overlap with arXiv:1912.01811

2105.02439 2021-05-07 cs.CV

Weakly Supervised Action Selection Learning in Video

Junwei Ma, Satya Krishna Gorti, Maksims Volkovs, Guangwei Yu

Comments CVPR 2021

2105.02400 2021-05-07 cs.CV eess.IV

SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery

Jaehyup Lee, Soomin Seo, Munchurl Kim

Comments Accepted to CVPR 2021

2105.01859 2021-05-07 cs.CV

Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors

Tao Yu, Zerong Zheng, Kaiwen Guo, Pengpeng Liu, Qionghai Dai, Yebin Liu

Comments CVPR 2021 Oral Paper, Project Page: http://www.liuyebin.com/Function4D/Function4D.html, THuman2.0 dataset available. Youtube: https://www.youtube.com/watch?v=-rWUn4fEQNU&t=126s

2103.05983 2021-05-07 cs.CV

Reformulating HOI Detection as Adaptive Set Prediction

Mingfei Chen, Yue Liao, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian

Comments Accepted to CVPR 2021

2105.02216 2021-05-06 cs.CV cs.LG cs.RO

Self-Supervised Multi-Frame Monocular Scene Flow

Junhwa Hur, Stefan Roth

Comments To appear at CVPR 2021. Code available: https://github.com/visinf/multi-mono-sf

2105.02201 2021-05-06 cs.CV

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao

Comments Accepted by CVPR 2021

2105.02173 2021-05-06 cs.CV

Learning Feature Aggregation for Deep 3D Morphable Models

Zhixiang Chen, Tae-Kyun Kim

Comments Published in CVPR 2021

2105.02047 2021-05-06 cs.CV

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Florian Kluger, Hanno Ackermann, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn

Comments CVPR 2021

2105.01879 2021-05-06 cs.CV cs.LG

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

Rui Huang, Yixuan Li

Comments Paper accepted as an oral presentation in CVPR'21

2104.14730 2021-05-06 cs.CV eess.IV

Perceptual Image Quality Assessment with Transformers

Manri Cheon, Sung-Jun Yoon, Byungyeon Kang, Junwoo Lee

Comments Accepted to NTIRE workshop at CVPR 2021. 1st Place in NTIRE 2021 perceptual IQA challenge. https://github.com/manricheon/IQT

2104.09052 2021-05-06 cs.LG

Metadata Normalization

Mandy Lu, Qingyu Zhao, Jiequan Zhang, Kilian M. Pohl, Li Fei-Fei, Juan Carlos Niebles, Ehsan Adeli

Comments Accepted to CVPR 2021. Project page: https://mml.stanford.edu/MDN/

2103.07969 2021-05-06 cs.CV cs.AI cs.LG

Monte Carlo Scene Search for 3D Scene Understanding

Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar, Chetan Srinivasa Kumar, Friedrich Fraundorfer, Vincent Lepetit

Comments To be presented at CVPR 2021

2104.10602 2021-05-05 cs.CV cs.AI

Visualizing Adapted Knowledge in Domain Transfer

Yunzhong Hou, Liang Zheng

Journal ref CVPR 2021

2102.01987 2021-05-05 cs.CV

Learning Graph Embeddings for Compositional Zero-shot Learning

Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata

Comments Accepted in IEEE CVPR 2021

2007.11365 2021-05-05 cs.CV

Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition

Sudhakar Kumawat, Manisha Verma, Yuta Nakashima, Shanmuganathan Raman

Comments Extended version of our CVPR 2019 work